{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JOW3CFTNXIFMQCXMBTYEQ5JRFO","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3788a4cd6135db6dfbb3845ffc2caa2a9687c23eeca29903508fe795cde1bc32","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-30T07:04:27Z","title_canon_sha256":"5be662cec7385b4569a93a7daadc8fb49f7b43f52a0142b48f2bc489ddc74cc8"},"schema_version":"1.0","source":{"id":"2606.00579","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.00579","created_at":"2026-06-02T01:03:58Z"},{"alias_kind":"arxiv_version","alias_value":"2606.00579v1","created_at":"2026-06-02T01:03:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00579","created_at":"2026-06-02T01:03:58Z"},{"alias_kind":"pith_short_12","alias_value":"JOW3CFTNXIFM","created_at":"2026-06-02T01:03:58Z"},{"alias_kind":"pith_short_16","alias_value":"JOW3CFTNXIFMQCXM","created_at":"2026-06-02T01:03:58Z"},{"alias_kind":"pith_short_8","alias_value":"JOW3CFTN","created_at":"2026-06-02T01:03:58Z"}],"graph_snapshots":[{"event_id":"sha256:aa28c98884a0b9b159c144816a2ffd6f71cbef4644392cd39674de1aafa083c2","target":"graph","created_at":"2026-06-02T01:03:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.00579/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As multimodal LLMs increasingly target video and audio, it is often assumed that such tasks require native omnimodal models. We show that this is not always the case: coding agents with only text+image access and a sandboxed tool-use interface can match, and in several settings outperform, SOTA native omnimodal models and predefined multimodal agent scaffolds across multiple audio-video benchmarks. Our trajectory analysis suggests that their strength comes from writing code and orchestrating tools to extract relevant evidence from transcripts, frames, and other modality signals, thereby conver","authors_text":"Dianqi Li, Dongping Chen, Qingyuan Shi, Tianyi Zhou, Xuanao Huang, Zhihan Hu","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-30T07:04:27Z","title":"Sandboxed Coding Agents are Competitive Omni-modal Task Solvers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00579","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:94dd2a72b2b6bca1495307b1410b45181c465cdd9c74d08a84e604d8f73192cb","target":"record","created_at":"2026-06-02T01:03:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3788a4cd6135db6dfbb3845ffc2caa2a9687c23eeca29903508fe795cde1bc32","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-30T07:04:27Z","title_canon_sha256":"5be662cec7385b4569a93a7daadc8fb49f7b43f52a0142b48f2bc489ddc74cc8"},"schema_version":"1.0","source":{"id":"2606.00579","kind":"arxiv","version":1}},"canonical_sha256":"4badb1166dba0ac80aec0cf04875312b8de5154bedcd1e1a8598fea68537a98d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4badb1166dba0ac80aec0cf04875312b8de5154bedcd1e1a8598fea68537a98d","first_computed_at":"2026-06-02T01:03:58.813730Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:03:58.813730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M/ahHFsIUX6JZq4gQLRnjOBTjZXDj9ipB6FZuPsd70tvTXioQ+T+Czdnyebp+OODoTF57ONisaKDCQmQXRZjDg==","signature_status":"signed_v1","signed_at":"2026-06-02T01:03:58.814131Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.00579","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:94dd2a72b2b6bca1495307b1410b45181c465cdd9c74d08a84e604d8f73192cb","sha256:aa28c98884a0b9b159c144816a2ffd6f71cbef4644392cd39674de1aafa083c2"],"state_sha256":"e263c8d73c74dae0c3387ba7451b5c8c35f4f4d82db3cde16ab48993b84b2079"}